Enhancing underwater images and videos by fusion

By Cosmin Ancuți, Codruta Orniana Ancuti, Tom Haber, Philippe Bekaert. 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012

1,107 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/4a61f6381d01eaff818d9cbb40cf83e182dd1188

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Color Balance and Fusion for Underwater Image Enhancement (2018, methodology): “[30] and our initial underwater approach [35]).”
Joint Rain Detection and Removal from a Single Image with Contextualized Deep Networks (2020, methodology): “It also includes the appearance of rain accumulation, by relying on the Koschmieder model that is approximately applicable to many turbid media, including mist, fog (e.g., [52]) and underwater (e.g., [53], [54]).”
An Underwater Color Image Quality Evaluation Metric (2015, background): “the images enhanced by image fusion method [6] obtain comparably better results.”
Enhancement of Underwater Images With Statistical Model of Background Light and Optimization of Transmission Map (2019, methodology): “Firstly, we collect over 2000 underwater images from a range of papers ([5], [12], [15], [16], [19], [21], [22], [27], [50], [50]) and from the YouTube, Google Images and Flickr.”
Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Dataset (2018, methodology): “Other methods aim for a visually pleasing result, e.g. [21], [22], [23], [24], [25], but have not shown color consistency that is required for scientiﬁc measurements.”
Using labeled data to evaluate change detectors in a multivariate streaming environment (2009, neutral): “To verify the effectiveness and superiority of FastICENet, we compare it with the most recent fast semantic segmentation networks on NWPU_YRCC_EX, NWPU_YRCC2, and Alberta River Ice Segmentation Dataset.”
Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding (2021, methodology): “[9] is not publicly available, we used the code 2 implemented by other researchers to realize code of [9].”
Transmission Estimation in Underwater Single Images (2013, background): “2The credits of the images: 3(a) courtesy of Nick Roberts; 3(f) [1]; 3(k) freeunderwaterimages.”
Simultaneous Enhancement and Super-Resolution of Underwater Imagery for Improved Visual Perception (2020, methodology): “Figure 6: Qualitative comparison of Deep SESR-enhanced images with SOTA models: RGHS [29], UCM [33], MSFusion [4], MS-Retinex [72], Water-Net [43], UGAN [20], Fusion-GAN [44], and FUnIE-GAN [35].”
Dense-Haze: A Benchmark for Image Dehazing with Dense-Haze and Haze-Free Images (2019, background): “The problem is related also to underwater image dehazing [11], [12], [13], [14].”
Underwater Image Enhancement by Dehazing With Minimum Information Loss and Histogram Distribution Prior (2016, positive): “Ancuti and Ancuti [19] proposed a novel strategy to enhance the visual quality of underwater images and videos based on the fusion principle.”
Deep Joint Rain Detection and Removal from a Single Image (2016, neutral): “[34, 2]).”
Underwater Image Enhancement With Hyper-Laplacian Reflectance Priors (2022, positive): “Ancuti et al. [2] developed a fusion-based enhancement method to blend different ﬁlters on single under-water input, and employed a multi-scale fusion strategy by applying white balance and global contrast techniques to improve raw images.”
Underwater Image Enhancement Using a Multiscale Dense Generative Adversarial Network (2020, methodology): “The literature [3] derives the inputs and weights from a raw underwater image.”
Underwater image dehazing using joint trilateral filter (2014, background): “two illumination images [3], white balanced image and color corrected image [1]).”
PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN With Dual-Discriminators (2023, methodology): “The nonphysical model methods mainly focus on the adjustment of image pixels, such as dynamic pixel range stretching [15], pixel distribution adjustment [16], and image fusion [17]–[19].”
Underwater Image Restoration Based on Image Blurriness and Light Absorption (2017, methodology): “The method [1] does poorly because contrast enhancement is often not effective for such images, and the white balancing of [1] sometimes introduces unwanted colors to the output images, such as the original images in the ﬁrst row of Fig.”
Automatic Red-Channel underwater image restoration (2015, methodology): “With any of the three possibilities, the hypothesis of the theorem is verified.”